© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 17132
    Prev
    Next
    INDEX
    Explanations

    food and drink consumables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hungry
    -0.11
     Hunger
    -0.11
     Foods
    -0.10
     hunger
    -0.09
    yahoo
    -0.09
     eas
    -0.09
     strugg
    -0.09
    bew
    -0.09
     Redemption
    -0.09
    oundingBox
    -0.09
    POSITIVE LOGITS
     beverages
    0.21
     drinks
    0.20
     drink
    0.20
    drink
    0.17
     Drink
    0.17
     beverage
    0.17
     shelter
    0.16
    Drink
    0.16
     Drinks
    0.15
     hydration
    0.14
    Activations Density 0.183%

    No Known Activations